Multi-cloud video distribution strategy optimization method and system

Abstract

The invention provides a multi-cloud video distribution strategy optimization method and system. The method comprises the following steps: acquiring live video stream data, CDN time delay data of each cloud platform server, CDN distribution price and transcoding price of each transcoding template in a historical time period; cleaning the live broadcast video stream data, counting the total amount of first audience terminals in a first time period of a historical time period, the minimum demand code rate proportion and the proportion of the number of live broadcast users corresponding to each source code rate, and performing user category classification according to the source video code rate and the minimum demand code rate of the audience terminals; predicting the total number of second audience terminals watching videos in a future predetermined time period, calculating the number of audience terminals corresponding to various users in the future predetermined time period, and respectively calculating each consumption cost and each QoE value of each user in the future predetermined time period based on each transcoding template; and determining a cloud platform server suitable for each type of users according to each consumption cost and each QoE value, and performing statistics on the proportion of the total number of users covered by each cloud platform server in a future predetermined time period.

Description

technical field [0001] The present invention relates to the field of multimedia technology, in particular to a multi-cloud video distribution strategy optimization method and system. Background technique [0002] For traditional CLS (Customer Link Service, user link service), it is very important for viewers to receive video streams smoothly, while traditional live multi-cloud video distribution strategy optimization systems usually build private data centers and The distribution network is used to realize the transcoding and distribution operations during the live broadcast. However, this often results in a waste of resources and high costs. Taking advantage of the advantages of the cloud platform, transferring the traditional video distribution architecture to the cloud, and using CDN (Content Delivery Network, Content Delivery Network) for distribution can effectively reduce operating costs and become the choice of more and more live broadcast service providers. However...

AI Technical Summary

Problems solved by technology

However, the above methods are only studied from the perspective of transcoding, and have not been combined with multi-CDN distribution to form a relatively complete evaluation and decision-making system

[0005] To sum up, most of the existing technologies focus on independent research and cost optimization on the selection of CDN distribution or transcoding templates. Although the above technologies reduce distribution costs to a certain extent, the consumption price of video distribution is not only affected by transcoding The impact of the price is also affected by the distribution price, so the cost optimization method commonly used in the prior art is limited to optimize the cost

Moreover, the above-mentioned technologies do not comprehensively consider the QoE (Quality of Experience) of the audience during the cost optimization process, so it is impossible to adopt a lower-cost allocation strategy on the premise of ensuring the QoE of the audience

Images